import pandas as pd
from woe_scoring import WOETransformer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

df = pd.read_csv("titanic_data.csv")
train, test = train_test_split(
    df, test_size=0.3, random_state=42, stratify=df["Survived"]
)

special_cols = [
    "PassengerId",
    "Survived",
    "Name",
    "Ticket",
    "Cabin",
]

cat_cols = [
    "Pclass",
    "Sex",
    "SibSp",
    "Parch",
    "Embarked",
]

encoder = WOETransformer(
    max_bins=8,
    min_pct_group=0.1,
    diff_woe_threshold=0.1,
    cat_features=cat_cols,
    special_cols=special_cols,
    n_jobs=-1,
    merge_type="chi2",
    generate_features=True,  # Enable feature generation
    max_generated_features=10,
)

encoder.fit(train, train["Survived"])
encoder.save_to_file("train_dict.json")

encoder.load_woe_iv_dict("train_dict.json")
encoder.refit(train, train["Survived"])

enc_train = encoder.transform(train)
enc_test = encoder.transform(test)

model = LogisticRegression()
model.fit(enc_train, train["Survived"])
test_proba = model.predict_proba(enc_test)[:, 1]

import pandas as pd
from woe_scoring import CreateModel
from sklearn.model_selection import train_test_split

df = pd.read_csv("titanic_data.csv")
train, test = train_test_split(
    df, test_size=0.3, random_state=42, stratify=df["Survived"]
)

special_cols = [
    "PassengerId",
    "Survived",
    "Name",
    "Ticket",
    "Cabin",
]

model = CreateModel(
    max_vars=5,
    special_cols=special_cols,
    selection_method="sfs",
    model_type="sklearn",
    gini_threshold=5.0,
    n_jobs=-1,
    random_state=42,
    class_weight="balanced",
    cv=3,
)
model.fit(train, train["Survived"])
test_proba = model.predict_proba(test[model.feature_names_])

print(model.coef_, model.intercept_)
print(model.feature_names_)

WOETransformer(
    max_bins=10,               # Maximum number of bins for each feature
    min_pct_group=0.05,        # Minimum percentage of each bin
    n_jobs=1,                  # Number of parallel jobs
    prefix="WOE_",             # Prefix for transformed features
    merge_type="chi2",         # Bin merging strategy ('chi2', 'woe', 'monotonic')
    cat_features=None,         # List of categorical features
    special_cols=None,         # Columns to exclude from transformation
    cat_features_threshold=0,  # Threshold for auto-identifying categorical features
    diff_woe_threshold=0.05,   # Minimum WOE difference between bins
    safe_original_data=False,  # Whether to keep original features
    generate_features=False,   # Whether to generate new features
    max_generated_features=20  # Max number of generated features to select
)

CreateModel(
    selection_method='rfe',    # Feature selection method ('rfe', 'sfs', 'iv')
    model_type='sklearn',      # Model implementation ('sklearn', 'statsmodel')
    max_vars=None,             # Maximum number of features to select
    special_cols=None,         # Columns to include as-is
    unused_cols=None,          # Columns to exclude
    n_jobs=1,                  # Number of parallel jobs
    gini_threshold=5.0,        # Minimum Gini score to keep a feature
    iv_threshold=0.05,         # Minimum IV threshold for feature selection
    corr_threshold=0.5,        # Correlation threshold for feature selection
    min_pct_group=0.05,        # Minimum percentage for each group
    random_state=None,         # Random seed for reproducibility
    class_weight='balanced',   # Class weighting strategy
    direction='forward',       # Direction for sequential feature selection
    cv=3,                      # Cross-validation folds
    l1_exp_scale=4,            # Exponent scale for L1 regularization
    l1_grid_size=20,           # Grid size for L1 regularization search
    scoring='roc_auc'          # Performance metric
)

encoder = WOETransformer(
    generate_features=True,    # Enable feature generation
    max_generated_features=20, # Select top 20 new features
    n_jobs=-1
)
encoder.fit(X, y)

# First fit the WOE transformer and model
encoder = WOETransformer()
encoder.fit(train, train["target"])
train_woe = encoder.transform(train)

model = CreateModel()
model.fit(train_woe, train["target"])

# Generate SQL query for scoring
sql_query = model.generate_sql(encoder)

# Save a credit scorecard to Excel
model.save_scorecard(
    encoder=encoder,
    path="output_dir",
    base_scorecard_points=600,  # Base score
    odds=50,                    # Base odds
    points_to_double_odds=20    # Points to double the odds
)

# Specify categorical features and their treatment
encoder = WOETransformer(
    cat_features=["education", "marital_status", "occupation"],
    max_bins=5,                 # Max bins for categorical features
    diff_woe_threshold=0.1,     # Merge bins with similar WOE values
    min_pct_group=0.05          # Minimum population percentage per bin
)